© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7660
    Prev
    Next
    INDEX
    Explanations

    references to numerical measurements, statistics, or quantity-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    553
    +0.13
    0.5%
    1978
    +0.13
    0.4%
    1865
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.13
    0.05
    1597
    +0.13
    0.03
    2036
    +0.11
    0.04
    Negative Logits
    Élet
    -0.58
    Mű
    -0.50
     despotism
    -0.48
    Bardzo
    -0.43
     riff
    -0.43
    født
    -0.42
     bezig
    -0.42
    deckt
    -0.42
     laissez
    -0.41
     autorytatywna
    -0.41
    POSITIVE LOGITS
     karton
    0.67
     silikon
    0.60
     Sén
    0.60
     Équipe
    0.60
     Messieurs
    0.60
     cincuenta
    0.58
     gmbh
    0.58
    fifty
    0.56
     Personne
    0.56
     sandra
    0.55
    Activations Density 0.179%

    No Known Activations